Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 203 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1036541 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0762. Min Act: -0.0002

Data Index: 515871 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0784. Min Act: -0.0001

Data Index: 283356 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0755. Min Act: -0.0001

Data Index: 108613 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1012035 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1128034 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0671. Min Act: -0.0001

Data Index: 143397 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0685. Min Act: -0.0001

Data Index: 26876 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0624. Min Act: -0.0002

Data Index: 882464 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0686. Min Act: -0.0001

Data Index: 2649 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1230306 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0652. Min Act: -0.0002

Data Index: 65546 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0640. Min Act: -0.0001

Data Index: 742940 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0630. Min Act: -0.0001

Data Index: 882217 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0606. Min Act: -0.0002

Data Index: 608080 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0630. Min Act: -0.0001

Data Index: 439273 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0628. Min Act: -0.0002

Data Index: 825189 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0645. Min Act: -0.0001

Data Index: 80876 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0621. Min Act: -0.0002

Data Index: 27305 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0597. Min Act: -0.0001

Data Index: 13505 (C4 (Web Text))

Max Activating Token Index: 677